© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118924
    Prev
    Next
    INDEX
    Explanations

    Coordination, proteasome, Q, Ponte

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ³,
    -0.05
     déjà
    -0.05
     '.')
    -0.05
     вже
    -0.05
     usual
    -0.05
     дър
    -0.05
     Resid
    -0.05
    guan
    -0.05
     běž
    -0.05
     resid
    -0.05
    POSITIVE LOGITS
     kutoka
    0.07
     ବ
    0.07
     ద్వారా
    0.07
     ڪرڻ
    0.07
    を通じて
    0.07
     According
    0.07
     использование
    0.07
     સમગ્ર
    0.07
    backup
    0.07
    চ্ছন্দ
    0.07
    Activations Density 0.002%

    No Known Activations